eu-ai-act-specialist

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a comprehensive regulatory compliance resource for the EU AI Act (Regulation EU 2024/1689), providing legitimate workflows, templates, and reference materials.
  • [SAFE]: Analysis of the included Python scripts (ai_risk_classifier.py, ai_compliance_checker.py, and ai_bias_detector.py) confirms they rely exclusively on the Python standard library. No external package dependencies or remote script downloads are present.
  • [SAFE]: No evidence of data exfiltration, hardcoded credentials, or sensitive file access was found. The scripts process user-provided JSON input and output results locally to the console or files.
  • [SAFE]: No obfuscation techniques, such as Base64 encoding, zero-width characters, or homoglyphs, were detected in any of the files.
  • [SAFE]: Indirect prompt injection risk is evaluated as safe; while the scripts ingest untrusted JSON data, their capabilities are restricted to mathematical calculations and text output, with no side effects like shell execution or network calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:08 AM